no code implementations • 22 Mar 2023 • Mohamad Shahbazi, Evangelos Ntavelis, Alessio Tonioni, Edo Collins, Danda Pani Paudel, Martin Danelljan, Luc van Gool
Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors.
no code implementations • 10 Dec 2022 • Zongwei Wu, Danda Pani Paudel, Deng-Ping Fan, Jingjing Wang, Shuo Wang, Cédric Demonceaux, Radu Timofte, Luc van Gool
In this work, we adapt such depth inference models for object segmentation using the objects' ``pop-out'' prior in 3D.
no code implementations • 2 Dec 2022 • Nikola Popovic, Danda Pani Paudel, Luc van Gool
Such representations are known to benefit from additional geometric and semantic supervision.
no code implementations • 14 Nov 2022 • Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, Luc van Gool
On the one hand, the proposed method learns to segment these planar hulls from the labeled data.
1 code implementation • 2 Aug 2022 • Zongwei Wu, Shriarulmozhivarman Gobichettipalayam, Brahim Tamadazte, Guillaume Allibert, Danda Pani Paudel, Cédric Demonceaux
In this work, we aim for RGB-D saliency detection that is robust to the low-quality depths which primarily appear in two forms: inaccuracy due to noise and the misalignment to RGB.
no code implementations • 3 Jun 2022 • Nikola Popovic, Danda Pani Paudel, Thomas Probst, Luc van Gool
It has since become a trend to use these five characteristics as a sufficient test, to determine whether or not gradient obfuscation is the main source of robustness.
1 code implementation • 11 May 2022 • Chuqiao Li, Zhiwu Huang, Danda Pani Paudel, Yabin Wang, Mohamad Shahbazi, Xiaopeng Hong, Luc van Gool
Within the proposed benchmark, we explore some commonly known essentials of standard continual learning.
no code implementations • 25 Mar 2022 • Ritika Chakraborty, Nikola Popovic, Danda Pani Paudel, Thomas Probst, Luc van Gool
However, multi-conditional image generation is a very challenging problem due to the heterogeneity and the sparsity of the (in practice) available conditioning labels.
1 code implementation • CVPR 2022 • Christoph Mayer, Martin Danelljan, Goutam Bhat, Matthieu Paul, Danda Pani Paudel, Fisher Yu, Luc van Gool
Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function.
Ranked #1 on
Visual Object Tracking
on LaSOT
(IS metric)
2 code implementations • CVPR 2022 • Junjie Ye, Changhong Fu, Guangze Zheng, Danda Pani Paudel, Guang Chen
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications.
1 code implementation • ICLR 2022 • Mohamad Shahbazi, Martin Danelljan, Danda Pani Paudel, Luc van Gool
On the contrary, we observe that class-conditioning causes mode collapse in limited data settings, where unconditional learning leads to satisfactory generative ability.
no code implementations • 30 Dec 2021 • Nikola Popovic, Danda Pani Paudel, Thomas Probst, Luc van Gool
We use linear layers with token-consistent stochastic parameters inside the multilayer perceptron blocks, without altering the architecture of the transformer.
no code implementations • 19 Dec 2021 • Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, Luc van Gool
We use a Transformer-based architecture to detect the keypoints, as well as to summarize the visual context of the image.
1 code implementation • CVPR 2022 • Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, Luc van Gool
We represent the road topology using a set of directed lane curves and their interactions, which are captured using their intersection points.
1 code implementation • ICCV 2021 • Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, Luc van Gool
In this work, we study the problem of extracting a directed graph representing the local road network in BEV coordinates, from a single onboard camera image.
1 code implementation • 10 Sep 2021 • Rui Gong, Martin Danelljan, Dengxin Dai, Danda Pani Paudel, Ajad Chhatkuli, Fisher Yu, Luc van Gool
In many real-world settings, the target domain task requires a different taxonomy than the one imposed by the source domain.
no code implementations • CVPR 2021 • Stefano d'Apolito, Danda Pani Paudel, Zhiwu Huang, Andres Romero, Luc van Gool
On the other hand, learning from inexpensive and intuitive basic categorical emotion labels leads to limited emotion variability.
no code implementations • 23 May 2021 • Guolei Sun, Yun Liu, Thomas Probst, Danda Pani Paudel, Nikola Popovic, Luc van Gool
This indicates that global scene context is essential, despite the seemingly bottom-up nature of the problem.
no code implementations • 18 May 2021 • Ankush Panwar, Pratyush Singh, Suman Saha, Danda Pani Paudel, Luc van Gool
The proposed method successfully adapts to the compound target domain consisting multiple new spoof types.
1 code implementation • CVPR 2021 • Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, Luc van Gool
Specifically, we show that: (1) our approach improves performance on all tasks when they are complementary and mutually dependent; (2) the CTRL helps to improve both semantic segmentation and depth estimation tasks performance in the challenging UDA setting; (3) the proposed ISL training scheme further improves the semantic segmentation performance.
1 code implementation • ICCV 2021 • Christoph Mayer, Martin Danelljan, Danda Pani Paudel, Luc van Gool
To tackle the problem of lacking ground-truth correspondences between distractor objects in visual tracking, we propose a training strategy that combines partial annotations with self-supervision.
Ranked #2 on
Visual Object Tracking
on OTB-2015
no code implementations • 26 Mar 2021 • Peshal Agarwal, Danda Pani Paudel, Jan-Nico Zaech, Luc van Gool
This paper aims at answering the question of finding the right strategy to make the target model robust and accurate in the setting of unsupervised domain adaptation without source data.
1 code implementation • CVPR 2021 • Mohamad Shahbazi, Zhiwu Huang, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool
To address this problem, we introduce a new GAN transfer method to explicitly propagate the knowledge from the old classes to the new classes.
no code implementations • ICCV 2021 • Guolei Sun, Thomas Probst, Danda Pani Paudel, Nikola Popovic, Menelaos Kanakis, Jagruti Patel, Dengxin Dai, Luc van Gool
Multiple tasks are performed by switching between them, performing one task at a time.
no code implementations • 31 Dec 2020 • Ayça Takmaz, Danda Pani Paudel, Thomas Probst, Ajad Chhatkuli, Martin R. Oswald, Luc van Gool
In this work, we present an unsupervised monocular framework for dense depth estimation of dynamic scenes, which jointly reconstructs rigid and non-rigid parts without explicitly modelling the camera motion.
no code implementations • 24 Dec 2020 • Dario Fuoli, Zhiwu Huang, Danda Pani Paudel, Luc van Gool, Radu Timofte
Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain.
1 code implementation • CVPR 2021 • Nikola Popovic, Danda Pani Paudel, Thomas Probst, Guolei Sun, Luc van Gool
Learning to perform spatially distributed tasks is motivated by the frequent availability of only sparse labels across tasks, and the desire for a compact multi-tasking network.
no code implementations • CVPR 2021 • Rui Gong, Yuhua Chen, Danda Pani Paudel, Yawei Li, Ajad Chhatkuli, Wen Li, Dengxin Dai, Luc van Gool
Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains.
1 code implementation • NeurIPS 2020 • Janine Thoma, Danda Pani Paudel, Luc V. Gool
Our soft assignment makes a gradual distinction between close and far images in both geometric and feature spaces.
1 code implementation • 19 Oct 2020 • Siwei Zhang, Zhiwu Huang, Danda Pani Paudel, Luc van Gool
In our formulation, we exploit a new method to enable the emotion prediction and the joint distribution learning in a unified adversarial learning game.
1 code implementation • 27 Aug 2020 • Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool
Image features for retrieval-based localization must be invariant to dynamic objects (e. g. cars) as well as seasonal and daytime changes.
no code implementations • 4 Jul 2020 • Rui Gong, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool
In this paper, we propose a unified SfM method, in which the matching process is supported by self-calibration constraints.
1 code implementation • 21 Mar 2020 • Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool
This is achieved by guiding the learning process such that the feature and geometric distances between images are directly proportional.
1 code implementation • ECCV 2020 • Clara Fernandez-Labrador, Ajad Chhatkuli, Danda Pani Paudel, Jose J. Guerrero, Cédric Demonceaux, Luc van Gool
This paper aims at learning category-specific 3D keypoints, in an unsupervised manner, using a collection of misaligned 3D point clouds of objects from an unknown category.
no code implementations • 15 Dec 2019 • Suman Saha, Wen-Hao Xu, Menelaos Kanakis, Stamatios Georgoulis, Yu-Hua Chen, Danda Pani Paudel, Luc van Gool
Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face recognition, that tries to prevent spoof attacks.
no code implementations • 23 Oct 2019 • Zhiwu Huang, Danda Pani Paudel, Guanju Li, Jiqing Wu, Radu Timofte, Luc van Gool
This paper introduces a divide-and-conquer inspired adversarial learning (DACAL) approach for photo enhancement.
no code implementations • ICCV 2019 • Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool
Notably, we further exploit the POP formulation of non-minimal solver also for the generic consensus maximization problems in 3D vision.
1 code implementation • CVPR 2019 • Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc van Gool
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions.
Ranked #1 on
Video Generation
on TrailerFaces
no code implementations • CVPR 2019 • Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Thomas Probst, Luc van Gool
The problem of localization often arises as part of a navigation process.
1 code implementation • 4 Oct 2018 • Dinesh Acharya, Zhiwu Huang, Danda Pani Paudel, Luc van Gool
Furthermore, we introduce a sliced version of Wasserstein GAN (SWGAN) loss to improve the distribution learning on the video data of high-dimension and mixed-spatiotemporal distribution.
no code implementations • ECCV 2018 • Danda Pani Paudel, Luc van Gool
This paper addresses the problem of robustly autocalibrating a moving camera with constant intrinsics.
no code implementations • ECCV 2018 • Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool
In this paper we present a method for incremental Non-Rigid Structure-from-Motion (NRSfM) with the perspective camera model and the isometric surface prior with unknown focal length.
no code implementations • ECCV 2018 • Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc van Gool
In this paper, we formulate the model-free consensus maximization as an Integer Program in a graph using `rules' on measurements.
no code implementations • 4 Dec 2017 • Zhiwu Huang, Bernhard Kratzwald, Danda Pani Paudel, Jiqing Wu, Luc van Gool
This paper presents a new problem of unpaired face translation between images and videos, which can be applied to facial video prediction and enhancement.
1 code implementation • 30 Nov 2017 • Bernhard Kratzwald, Zhiwu Huang, Danda Pani Paudel, Acharya Dinesh, Luc van Gool
In this paper, we aim to improve the state-of-the-art video generative adversarial networks (GANs) with a view towards multi-functional applications.
no code implementations • ICCV 2017 • Danda Pani Paudel, Adlane Habed, Luc van Gool
This paper addresses the problem of estimating the geometric transformation relating two distinct visual modalities (e. g. an image and a map, or a projective structure and a Euclidean 3D model) while relying only on semantic cues, such as semantically segmented regions or object bounding boxes.
no code implementations • CVPR 2017 • Pablo Speciale, Danda Pani Paudel, Martin R. Oswald, Till Kroeger, Luc van Gool, Marc Pollefeys
While randomized methods like RANSAC are fast, they do not guarantee global optimality and fail to manage large amounts of outliers.
1 code implementation • 8 Jun 2017 • Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc van Gool
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions.
no code implementations • ICCV 2015 • Danda Pani Paudel, Adlane Habed, Cedric Demonceaux, Pascal Vasseur
This paper deals with the problem of registering a known structured 3D scene and its metric Structure-from-Motion (SfM) counterpart.
no code implementations • CVPR 2015 • Danda Pani Paudel, Adlane Habed, Cedric Demonceaux, Pascal Vasseur
This paper investigates the problem of registering a scanned scene, represented by 3D Euclidean point coordinates, and two or more uncalibrated cameras.
no code implementations • CVPR 2014 • Adlane Habed, Danda Pani Paudel, Cedric Demonceaux, David Fofi
We present a new globally optimal algorithm for self-calibrating a moving camera with constant parameters.